Automated analysis of protein subcellular location in time series images

Hu, Yanhua; Osuna-Highley, Elvira; Hua, Juchang; Nowicki, Theodore S.; Stolz, Robert; McKayle, Camille; Murphy, Robert F.

doi:10.1093/bioinformatics/btq239

Cited by 14 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The overall accuracy of the automated RBC classification algorithm was 91·9% for low resolution and 75·3% for high resolution. This compares favourably with the general accuracy of automated image analysis methods throughout other areas, particularly for the low‐resolution classification . Interestingly, the majority of incorrectly categorized cells (high resolution) in the test set were categorized as one of the neighbouring morphologies along the transition from discocyte to spherocyte (e.g.…”

Section: Discussionmentioning

confidence: 66%

“…Figure shows a confusion matrix (a method commonly used for evaluating the accuracy of automated classifications) for the morphology classifications based on the multiparameter cluster analysis algorithm. To produce the confusion matrix, we selected a random set of images of 1000 single stored RBCs (test set) from the set of all images and classified the morphology of each individual RBC via visual examination (‘true class’) and by applying the automated classification (‘algorithm‐predicted class’).…”

Section: Resultsmentioning

confidence: 99%

“…The cell classification algorithm was optimized using a manually categorized training set of 1000 randomly selected individual RBCs, taken from the entire set (n = 1 367 852) of images of single stored RBCs acquired using the system. Figure 4 shows a confusion matrix (a method commonly used for evaluating the accuracy of automated classifications) [34,35] for the morphology classifications based on the multiparameter cluster analysis algorithm. To produce the confusion matrix, we selected a random set of images of 1000 single stored RBCs (test set) from the set of all images and classified the morphology of each individual RBC via visual examination ('true class') and by applying the automated classification ('algorithmpredicted class').…”

Section: Automated Classification Of Individual Rbc Morphologymentioning

confidence: 99%

See 2 more Smart Citations

Quantifying morphological heterogeneity: a study of more than 1 000 000 individual stored red blood cells

et al. 2015

View full text Add to dashboard Cite

Background and Objectives The morphology of red blood cells (RBCs) deteriorates progressively during hypothermic storage. The degree of deterioration varies between individual cells, resulting in a highly heterogeneous population of cells contained within each RBC unit. Current techniques capable of categorizing the morphology of individual stored RBCs are manual, laborious, error-prone procedures that limit the number of cells that can be studied. Our objective was to create a simple, automated system for high-throughput RBC morphology classification. Materials and Methods A simple microfluidic device, designed to enable rapid, consistent acquisition of images of optimally oriented RBCs, was fabricated using soft lithography. A custom image analysis algorithm was developed to categorize the morphology of each individual RBC in the acquired images. The system was used to determine morphology of individual RBCs in several RBC units stored hypothermically for 6–8 weeks. Results The system was used to automatically determine the distribution of cell diameter within each morphological class for >1,000,000 individual stored RBCs (speed: >10,000 cells/hour; accuracy: 91.9% low-resolution, 75.3% high-resolution). Diameter mean and standard deviation by morphology class: discocyte 7.80±0.49μm, echinocyte 1 7.61±0.63μm, echinocyte 2 7.02±0.61μm, echinocyte 3 6.47±0.42μm, sphero-echinocyte 6.01±0.26μm, spherocyte 6.02±0.27μm, stomatocyte 1 6.95±0.61μm, stomatocyte 2 7.32 ± 0.47μm. Conclusion The automated morphology classification procedure described in this study is significantly simpler, faster and less subjective than conventional manual procedures. The ability to evaluate the morphology of individual RBCs automatically, rapidly and in statistically significant numbers enabled us to perform the most extensive study of stored RBC morphology to date.

show abstract

Section: Discussionmentioning

confidence: 66%

Section: Resultsmentioning

confidence: 99%

Section: Automated Classification Of Individual Rbc Morphologymentioning

confidence: 99%

See 1 more Smart Citation

Quantifying morphological heterogeneity: a study of more than 1 000 000 individual stored red blood cells

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Currently, there are no general protocols for image-based quantitative analysis that cover all plant organelles. Various aspects of imaging analysis, such as image processing, pattern recognition algorithms, machine learning and statistical modeling, have recently advanced (Coelho et al 2010 , Hu et al 2010 , Langhammer et al 2010 ). Indeed, endoplasmic reticulum body mutants in Arabidopsis were isolated using image-based quantitative analysis (Nagano et al 2009 ).…”

Section: Discussionmentioning

confidence: 99%

The Plant Organelles Database 2 (PODB2): An Updated Resource Containing Movie Data of Plant Organelle Dynamics

Mano

Miwa

Nishikawa

et al. 2010

Plant and Cell Physiology

View full text Add to dashboard Cite

The Plant Organelles Database (PODB) was launched in 2006 and provides imaging data of plant organelles, protocols for plant organelle research and external links to relevant websites. To provide comprehensive information on plant organelle dynamics and accommodate movie files that contain time-lapse images and 3D structure rotations, PODB was updated to the next version, PODB2 (http://podb.nibb.ac.jp/Organellome). PODB2 contains movie data submitted directly by plant researchers and can be freely downloaded. Through this organelle movie database, users can examine the dynamics of organelles of interest, including their movement, division, subcellular positioning and behavior, in response to external stimuli. In addition, the user interface for access and submission has been enhanced. PODB2 contains all of the information included in PODB, and the volume of data and protocols deposited in the PODB2 continues to grow steadily. Moreover, a new website, Plant Organelles World (http://podb.nibb.ac.jp/Organellome/PODBworld/en/index.html), which is based on PODB2, was recently launched as an educational tool to engage members of the non-scientific community such as students and school teachers. Plant Organelles World is written in layman's terms, and technical terms were avoided where possible. We would appreciate contributions of data from all plant researchers to enhance the usefulness of PODB2 and Plant Organelles World.

show abstract

“…For instance, the structures and functions of different proteins were studied based on their locations in specific organelles using image classification models [13][14][15][16]. In [17,18], mixture patterns of protein distributions were recognized and [19] proposed to identify protein distribution patterns in time series images. In [20,21], generative models were trained from microscopy images to capture variations of protein distributions from cell to cell.…”

mentioning

confidence: 99%

Robust classification and detection with applications in biomedical images

Lin¹

View full text Add to dashboard Cite

Foremost, I would like to express my deepest gratitude to my supervisor, Associate Professor Lin Zhiping and co-supervisor, Professor Liu Ai Qun for their constant support, professional guidance and continuous encouragement through my four years of Ph.D. study and research. Without their insightful comments and constructive suggestions, I would not have completed my Ph.D. research and this thesis. Their insightful, passionate and strict attitude towards research works will continuously benefit me throughout my lifetime. I would also show my gratitude to Professor Kar-Ann Toh, Associate Professor Sun Lei and Dr. Zhang Jing Bo for providing great help and support to my research works. I sincerely thank the technicians from the Center for Bio Devices and Signal Analysis for their technical support during my Ph.D. study. I would like to thank Nanyang Technological University for the four years financial support of my Ph.D. scholarship. During the years of my Ph.D. study, I have been in the company of numerous wonderful friends. I have enjoyed spending my time with Mr. Liang Yunfeng, Mr. Peng Siyuan, and Mr. Zhuang Huiping. I benefit a lot from their help in my daily life. Finally, and most importantly, I would like to thank my beloved family for the endless love and unconditional support throughout the journey of my study.

show abstract

Automated analysis of protein subcellular location in time series images

Abstract: murphy@cmu.edu.

Cited by 14 publications

References 20 publications

Quantifying morphological heterogeneity: a study of more than 1 000 000 individual stored red blood cells

Quantifying morphological heterogeneity: a study of more than 1 000 000 individual stored red blood cells

The Plant Organelles Database 2 (PODB2): An Updated Resource Containing Movie Data of Plant Organelle Dynamics

Robust classification and detection with applications in biomedical images

Contact Info

Product

Resources

About